[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273515-105":59,"doc-detail-273515-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","temporal-leakage-in-financial-news-nlp-a-multi-architecture-audit-with-a-regime-specific-ma-signal","Temporal Leakage in Financial News NLP - A Multi-Architecture Audit with a Regime-Specific M&A Signal","","Financial-news direction prediction is a widely used NLP benchmark, yet reported improvements vary sharply with train–test protocol, especially whether splits are chronological or random. This study audits temporal leakage across a 49,799-article corpus using 16 feature–model pipelines (TF-IDF, MiniLM, FinBERT, fine-tuned RoBERTa/DeBERTa) and LLM probes (zero/few-shot and LoRA). Random splits inflate MCC substantially, while only M&A shows a near-temporal locked-test signal under strict evaluation, with the effect not transferring to a separate U.S. dataset.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/temporal-leakage-in-financial-news-nlp-a-multi-architecture-audit-with-a-regime-specific-ma-signal/273515/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/temporal-leakage-in-financial-news-nlp-a-multi-architecture-audit-with-a-regime-specific-ma-signal/273515.png","ImageObject",300,407,{"name":92,"@type":93},"Ivy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-07","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":56},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is temporal leakage in financial-news NLP benchmarks?","Question",{"text":112,"@type":113},"Temporal leakage refers to inflated performance when training and test splits are not properly separated in time, letting models exploit regime-correlated vocabulary, entities, and label structure.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How do random and chronological splits affect model performance?",{"text":117,"@type":113},"Random splits significantly increase MCC relative to chronological splits, and the gap grows with model capacity and feature richness.",{"name":119,"@type":110,"acceptedAnswer":120},"Which event category retains a signal under near-temporal chronological evaluation?",{"text":121,"@type":113},"Mergers and acquisitions (M&A) is the only audited category with a positive locked-test signal under near-temporal chronological evaluation, and the headline-level effect does not transfer to a U.S. corpus.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},273515,1789471829,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":56,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","Temporal Leakage in Financial News NLP:  \nA Multi-Architecture Audit with a Regime-Specific M&A Signal  \nChenhao Xue1,2 , Raslen Guesmi1 , Siwei Feng1 , Yucheng Gong1,3  \nJacob Xavier Sundram 1,3 , Jordan Pang 1,3 , Lan Wang4 , Julian Kaljuvee* 1  \n1Predictive Labs Ltd 2University of Oxford 3Imperial College London 4Independent Researcher  \narXiv : 2608 . 17223v2 [cs .CL] 6 Sep 2026  \nAbstract  \nFinancial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train–test split is chronological or random, i.e., on temporal leakage. We audit this dependence on a 49,799-article corpus across  \n16 feature–model combinations spanning TF-IDF, MiniLM, FinBERT, and fine-tuned RoBERTa-large / DeBERTa-v3-large, plus separate zero/few-shot and LoRA probes of Llama-3 and Qwen2.5 LLMs: random splits inflate MCC by 1.1 × to 6.5 ×, tracking model capacity and feature richness, and end-to-end FinBERT fine-tuning re-amplifies rather than closes the gap (size-matched ratio  \n1.75 ×) . Conditioning on event type, mergersand acquisitions (M&A) is the only audited category with a positive locked-test signal under near-temporal chronological evaluation (TF-IDF MCC = 0 . 138 train-only, 0.068 under train∪val refit; 10 ,000-permutation p \u003C 10 −3); the signal does not transfer to FNSPID’s 2009–2020 U.S. corpus, localising the headline to our 2024–2025 European-tilted M&A semantics rather than a universal predictor. Three independent role labellers converge on acquirer-tagged articles as the signal locus, a power-limited qualitative convergence rather than a hypothesis-tested asymmetry. Chronological splitting plays for financial NLP the role characteristics-purging plays for asset pricing: it strips the predictable, stale component of news and leaves a residual that is small, event-localized, and lexically shallow. We advocate leakage audits as a required disclosure for financial-NLP benchmarks. We open-source our data and code at [https:](https:)//[github.com/ChenHX111/Temporal_](github.com/ChenHX111/Temporal_)[Leakage_in_Financial_News_NLP](Leakage_in_Financial_News_NLP.)[.](Leakage_in_Financial_News_NLP.)  \n1 Introduction  \n1.1 Motivation: Financial News Prediction asan NLP Benchmark  \nFinancial-news direction prediction is one of the most contested empirical benchmarks at the NLP–  \nfinance boundary: text-understanding capability is tested against an economically grounded outcome signal. A decade of work, spanning structured event embeddings (Ding et al., 2014, 2015), recurrent models over tweets and prices (Xu and Cohen, 2018 ; Hu et al., 2018), domain-adapted LMs (Araci, 2019 ; Yang et al., 2020b), and LLMbased approaches (Lopez-Lira and Tang, 2023 ; Liet al., 2024 ; Wang et al., 2024 ; Xie et al., 2024), has produced an optimistic narrative: per-paper directional-accuracy figures in the high-50s to mid- 60s (e.g., 58.2% binary accuracy on StockNet tweets (Xu and Cohen, 2018); 64.2% S&P directional accuracy Ding et al., 2015) . The premise is worth taking seriously; the evidence is not.  \nFinancial NLP inherits a structural vulnerability: news articles, firm identities, market regimes, and return labels are jointly temporally autocorrelated, and modern language models exploit that structure. A model trained on a random half of a year’s financial news absorbs the vocabulary, entity graph, and return correlations of the same market cycle as its test set: regime memorisation that differs qualitatively from within-sample overfitting. A random split holding out individual articles from the early- 2024 AI rally, the late-2024 rate-cut pivot, or the 2025 European M&A wave in our own corpus lets a classifier exploit regime-context cues unavailable in a prospective chronological test. This concern is well-documented in financial machine learning (López de Prado, 2018 ; Bailey et al., 2014 ; Kapoor and Narayanan, 2023 ; Hewamalage et al., 2023 ; Bergmeir and Benítez, 2012) and, separately, in NLP e","cbCaioEON8oekyWM","https://ap.wps.com/l/cbCaioEON8oekyWM","pdf",683777,34,"English","# Abstract\n# Introduction\n## Motivation: Financial News Prediction as an NLP Benchmark\n## Central Research Questions\n## Main Findings","[{\"question\":\"What is temporal leakage in financial-news NLP benchmarks?\",\"answer\":\"Temporal leakage refers to inflated performance when training and test splits are not properly separated in time, letting models exploit regime-correlated vocabulary, entities, and label structure.\"},{\"question\":\"How do random and chronological splits affect model performance?\",\"answer\":\"Random splits significantly increase MCC relative to chronological splits, and the gap grows with model capacity and feature richness.\"},{\"question\":\"Which event category retains a signal under near-temporal chronological evaluation?\",\"answer\":\"Mergers and acquisitions (M\\u0026A) is the only audited category with a positive locked-test signal under near-temporal chronological evaluation, and the headline-level effect does not transfer to a U.S. corpus.\"}]","Temporal Leakage in Financial News NLP - A Multi-Architecture Audit with a Regime-Specific M&A Signal | PDF",86]